Assessing experienced tranquillity through natural language processing and landscape ecology measures

Flurina M Wartmann; Olga Koblet; Ross S Purves

doi:10.1007/s10980-020-01181-8

Assessing experienced tranquillity through natural language processing and landscape ecology measures

Landsc Ecol. 2021;36(8):2347-2365. doi: 10.1007/s10980-020-01181-8. Epub 2021 Jan 27.

Authors

Flurina M Wartmann^{1

2}, Olga Koblet³, Ross S Purves³

Affiliations

¹ School of Geosciences, University of Aberdeen, St Mary's, Elphinstone Road, Aberdeen, AB24 3UF UK.
² Swiss Federal Institute for Forest, Snow and Landscape Research (WSL), Zürcherstrasse 111, 8903 Birmensdorf, Switzerland.
³ Department of Geography, University of Zurich, Winterthurerstrasse 190, 8057 Zurich, Switzerland.

Abstract

Context: Identifying tranquil areas is important for landscape planning and policy-making. Research demonstrated discrepancies between modelled potential tranquil areas and where people experience tranquillity based on field surveys. Because surveys are resource-intensive, user-generated text data offers potential for extracting where people experience tranquillity.

Objectives: We explore and model the relationship between landscape ecological measures and experienced tranquillity extracted from user-generated text descriptions.

Methods: Georeferenced, user-generated landscape descriptions from Geograph.UK were filtered using keywords related to tranquillity. We stratify resulting tranquil locations according to dominant land cover and quantify the influence of landscape characteristics including diversity and naturalness on explaining the presence of tranquillity. Finally, we apply natural language processing to identify terms linked to tranquillity keywords and compare the similarity of these terms across land cover classes.

Results: Evaluation of potential keywords yielded six keywords associated with experienced tranquillity, resulting in 15,350 extracted tranquillity descriptions. The two most common land cover classes associated with tranquillity were arable and horticulture, and improved grassland, followed by urban and suburban. In the logistic regression model across all land cover classes, freshwater, elevation and naturalness were positive predictors of tranquillity. Built-up area was a negative predictor. Descriptions of tranquillity were most similar between improved grassland and arable and horticulture, and most dissimilar between arable and horticulture and urban.

Conclusions: This study highlights the potential of applying natural language processing to extract experienced tranquillity from text, and demonstrates links between landscape ecological measures and tranquillity as a perceived landscape quality.

Supplementary information: The online version of this article (10.1007/s10980-020-01181-8) contains supplementary material, which is available to authorized users.

Keywords: Landscape perception; Landscape quality; Natural language processing; Tranquillity mapping; User-generated content.